{"id":"W2157202661","doi":"10.1111/j.1365-2929.2005.02092.x","title":"Assessment in the context of uncertainty: how many members are needed on the panel of reference of a script concordance test?","year":2005,"lang":"en","type":"article","venue":"Medical Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":151,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Concordance; Cronbach's alpha; Statistics; Context (archaeology); Sample size determination; Reliability (semiconductor); Panel analysis; Test (biology); Panel data; Correlation; Sample (material); Medicine; Kappa; Mathematics; Psychometrics; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03577259,0.0005425029,0.0009750674,0.001869355,0.0009686531,0.001541431,0.001181436,0.001087615,0.001946061],"category_scores_gemma":[0.1663144,0.0003455591,0.000603592,0.001212447,0.001338554,0.002183537,0.002110693,0.0009205653,0.0006897546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000883523,"about_ca_system_score_gemma":0.001358508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001314768,"about_ca_topic_score_gemma":0.001860287,"domain_scores_codex":[0.9552462,0.0265673,0.003877288,0.002460088,0.01108564,0.000763445],"domain_scores_gemma":[0.8914131,0.06129483,0.02035431,0.006690531,0.01725409,0.002993238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00160267,0.0002604846,0.7530351,0.0004382117,0.0003130719,0.000951717,0.01123447,0.002019121,0.006437358,0.0006103572,0.003246745,0.2198508],"study_design_scores_gemma":[0.0001077123,0.003321733,0.9208923,0.0009254214,0.0004166056,0.007328215,0.01535088,0.02129952,0.01833944,0.003632557,0.008120531,0.0002651283],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9799352,0.0006813784,0.01578305,0.0006623033,0.00009031761,0.0001269959,0.0001201542,0.000110332,0.002490306],"genre_scores_gemma":[0.9824364,0.0002207804,0.0165419,0.0001407702,0.00006491203,0.00013588,0.0001476966,0.00002116301,0.0002905562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03577259,"threshold_uncertainty_score":0.1891858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05041126147914685,"score_gpt":0.3757654797721233,"score_spread":0.3253542182929764,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}